AdvGAN++ : Harnessing latent layers for adversary generation
Preprint
Abstract
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input image as a prior for generating adversaries to target a model. In this work, we show how latent features can serve as better priors than input images for adversary generation by proposing AdvGAN++, a version of AdvGAN that achieves higher attack rates than AdvGAN and at the same time generates perceptually realistic images on MNIST and CIFAR-10 datasets.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Adaptive Adversarial Attack on Scene Text Recognition2020
- Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models2019
- Targeted Adversarial Examples for Black Box Audio Systems2019
- Adversarial Examples in the Physical World2018
- Deep Residual Learning for Image Recognition2016
- Wide Residual Networks2016